{"id":"https://openalex.org/W7134267786","doi":"https://doi.org/10.3390/systems14030292","title":"A Novel Portfolio Selection Method via Deep Reinforcement Learning","display_name":"A Novel Portfolio Selection Method via Deep Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134267786","doi":"https://doi.org/10.3390/systems14030292"},"language":"en","primary_location":{"id":"doi:10.3390/systems14030292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems14030292","pdf_url":"https://www.mdpi.com/2079-8954/14/3/292/pdf?version=1773071236","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2079-8954/14/3/292/pdf?version=1773071236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040506900","display_name":"Ni Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I180632629","display_name":"Xi'an International Studies University","ror":"https://ror.org/05gcme754","country_code":"CN","type":"education","lineage":["https://openalex.org/I180632629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni Gao","raw_affiliation_strings":["School of Economics and Finance, Xi\u2019an International Studies University, Xi\u2019an 710128, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Finance, Xi\u2019an International Studies University, Xi\u2019an 710128, China","institution_ids":["https://openalex.org/I180632629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128574804","display_name":"Yan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I180632629","display_name":"Xi'an International Studies University","ror":"https://ror.org/05gcme754","country_code":"CN","type":"education","lineage":["https://openalex.org/I180632629"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["School of Economics and Finance, Xi\u2019an International Studies University, Xi\u2019an 710128, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Finance, Xi\u2019an International Studies University, Xi\u2019an 710128, China","institution_ids":["https://openalex.org/I180632629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940873","display_name":"Yiyue He","orcid":null},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyue He","raw_affiliation_strings":["School of Economics and Management, Northwest University, Xi\u2019an 710127, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Management, Northwest University, Xi\u2019an 710127, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128569606","display_name":"Juan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I88830068","display_name":"Shaanxi Normal University","ror":"https://ror.org/0170z8493","country_code":"CN","type":"education","lineage":["https://openalex.org/I88830068"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Zhang","raw_affiliation_strings":["School of Journalism and Communication, Shaanxi Normal University, Xi\u2019an 710019, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Journalism and Communication, Shaanxi Normal University, Xi\u2019an 710019, China","institution_ids":["https://openalex.org/I88830068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071899198","display_name":"Lefang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefang Zhang","raw_affiliation_strings":["School of Economics and Finance, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics and Finance, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100940873"],"corresponding_institution_ids":["https://openalex.org/I37802460"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35060079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":"3","first_page":"292","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.8374000191688538,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.8374000191688538,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.040300000458955765,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8428000211715698},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.5389999747276306},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.536899983882904},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5059999823570251},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4609000086784363},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.39340001344680786},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.35100001096725464},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.34439998865127563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8428000211715698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648999810218811},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.536899983882904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5091999769210815},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5059999823570251},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.35100001096725464},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C91602232","wikidata":"https://www.wikidata.org/wiki/Q756115","display_name":"Volatility (finance)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C202655437","wikidata":"https://www.wikidata.org/wiki/Q7231728","display_name":"Portfolio optimization","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C139819358","wikidata":"https://www.wikidata.org/wiki/Q462748","display_name":"Asset allocation","level":3,"score":0.3192000091075897},{"id":"https://openalex.org/C74510933","wikidata":"https://www.wikidata.org/wiki/Q1936145","display_name":"Project portfolio management","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3068999946117401},{"id":"https://openalex.org/C2776517139","wikidata":"https://www.wikidata.org/wiki/Q873442","display_name":"Asset management","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C103144560","wikidata":"https://www.wikidata.org/wiki/Q2670999","display_name":"Investment strategy","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2778865806","wikidata":"https://www.wikidata.org/wiki/Q6060850","display_name":"Investment decisions","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C181236170","wikidata":"https://www.wikidata.org/wiki/Q848354","display_name":"Capital asset pricing model","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C131562839","wikidata":"https://www.wikidata.org/wiki/Q1574928","display_name":"Trading strategy","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/systems14030292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems14030292","pdf_url":"https://www.mdpi.com/2079-8954/14/3/292/pdf?version=1773071236","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6efe62d1c6d443de8c3a690444c316a0","is_oa":true,"landing_page_url":"https://doaj.org/article/6efe62d1c6d443de8c3a690444c316a0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Systems, Vol 14, Iss 3, p 292 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/systems14030292","is_oa":true,"landing_page_url":"https://doi.org/10.3390/systems14030292","pdf_url":"https://www.mdpi.com/2079-8954/14/3/292/pdf?version=1773071236","source":{"id":"https://openalex.org/S4210219410","display_name":"Systems","issn_l":"2079-8954","issn":["2079-8954"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328010","display_name":"Yakult Bio-Science Foundation","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134267786.pdf","grobid_xml":"https://content.openalex.org/works/W7134267786.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Portfolio":[0],"selection":[1,81],"is":[2,119,144],"a":[3,42,78,90,137,208],"fundamental":[4],"task":[5],"in":[6,28,132,217],"quantitative":[7],"finance":[8],"that":[9,171,206],"aims":[10,98,107],"to":[11,16,50,99,108,122,146,155,190],"allocate":[12],"capital":[13],"across":[14],"assets":[15],"balance":[17],"risk":[18],"and":[19,37,59,104,130,152,179,203,214],"return.":[20],"While":[21],"deep":[22,85,181],"learning":[23,134],"has":[24],"shown":[25],"great":[26],"promise":[27],"this":[29],"field,":[30],"extracting":[31],"reliable":[32],"feature":[33,92],"representations":[34],"from":[35],"non-stationary":[36],"noisy":[38],"financial":[39,177,219],"data":[40],"remains":[41],"significant":[43],"challenge.":[44],"The":[45,184],"existing":[46],"models":[47],"often":[48],"fail":[49],"simultaneously":[51],"capture":[52,109],"the":[53,105,124,133,161],"temporal":[54,101],"dynamics":[55,103],"of":[56,126],"price":[57],"series":[58],"complex":[60],"inter-asset":[61],"correlations,":[62,111],"which":[63],"limits":[64],"their":[65],"trading":[66],"performance.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"we":[72],"propose":[73],"Denoising-Sequence-Correlation":[74],"Reinforcement":[75],"Learning":[76],"(DSCRL),":[77],"novel":[79],"portfolio":[80,150],"framework":[82],"based":[83],"on":[84,166],"reinforcement":[86,182],"learning.":[87],"DSCRL":[88,172,199],"employs":[89],"dual-stream":[91],"extraction":[93],"network,":[94],"where":[95],"one":[96],"stream":[97],"learn":[100],"market":[102],"other":[106],"asset":[110],"enabling":[112],"more":[113],"informative":[114],"representations.":[115],"A":[116],"denoising":[117],"module":[118],"further":[120],"integrated":[121],"mitigate":[123],"impact":[125],"noise,":[127],"ensuring":[128],"stability":[129],"robustness":[131],"process.":[135],"Furthermore,":[136],"deterministic":[138],"policy":[139],"gradient":[140],"(DPG)-based":[141],"decision":[142],"network":[143],"designed":[145],"directly":[147],"optimize":[148],"continuous":[149],"weights":[151],"normalize":[153],"them":[154],"satisfy":[156],"budget":[157],"constraints":[158],"while":[159],"preserving":[160],"importance.":[162],"Extensive":[163],"experiments":[164],"conducted":[165],"multiple":[167],"benchmark":[168],"datasets":[169],"demonstrate":[170],"consistently":[173],"outperforms":[174],"both":[175],"traditional":[176],"heuristics":[178],"advanced":[180],"approaches.":[183],"results":[185],"highlight":[186],"its":[187],"superior":[188],"ability":[189],"achieve":[191],"higher":[192],"cumulative":[193],"returns":[194],"with":[195],"lower":[196],"volatility.":[197],"Overall,":[198],"provides":[200],"an":[201],"effective":[202],"robust":[204],"solution":[205],"strikes":[207],"better":[209],"trade-off":[210],"between":[211],"pursuing":[212],"profits":[213],"managing":[215],"risks":[216],"dynamic":[218],"markets.":[220]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-10T00:00:00"}